Skeletonization of Deformed CAPTCHAs Based on Pixel Depth

CAPTCHA is a security technology that presents test to tell computers and humans apart. Nowadays the most widely deployed CAPTCHAs are text-based schemes, which rely on sophisticated distortion of text images aimed at rendering them unrecognizable to the state of the art of pattern recognition methods. Generally, the skeletonization of character is acknowledged as one of the most significant part in character recognition. In this paper, a depth-based approach is proposed in order to locate the skeleton point. Experiments show that the depth-based skeletonization scheme is applicable to the widely used CAPTCHA images, and the skeleton is robust against rotated, distorted or conglutinated characters.

[1]  Yang Peng,et al.  A 3-layer Dynamic CAPTCHA Implementation , 2010, 2010 Second International Workshop on Education Technology and Computer Science.

[2]  Yuan Yan Tang,et al.  Wavelet-Based Approach to Character Skeleton , 2007, IEEE Transactions on Image Processing.

[3]  Rik D. T. Janssen.  INTERPRETATION OF MAPS: FROM BOTTOM-UP TO MODEL-BASED , 1997 .

[4]  John Langford,et al.  Telling humans and computers apart automatically , 2004, CACM.

[5]  Tong-Yee Lee,et al.  Curve-Skeleton Extraction Using Iterative Least Squares Optimization , 2008, IEEE Transactions on Visualization and Computer Graphics.

[6]  Xia Wang,et al.  A CAPTCHA Implementation Based on Moving Objects Recognition Problem , 2010, 2010 International Conference on E-Business and E-Government.

[7]  Jeff Yan,et al.  The robustness of a new CAPTCHA , 2010, EUROSEC '10.

[8]  Mian Yang,et al.  The skeletonization research of low-quality Chinese characters based on principal curves , 2009, 2009 International Conference on Machine Learning and Cybernetics.